iPad mini (5th generation)
Geekbench AI Score
661
Single Precision Score
1112
Half Precision Score
1002
Quantized Score
Geekbench AI 1.2.0 for iOS AArch64
Result Information
| Upload Date | December 03 2024 11:48 PM |
| Views | 1 |
System Information
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A12 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 18.1.1 |
| Model | iPad mini (5th generation) |
| Model ID | iPad11,2 |
| Motherboard | J211AP |
| CPU Information | |
|---|---|
| Name | Apple A12 Bionic |
| Topology | 1 Processor, 6 Cores |
| Identifier | ARM |
| Base Frequency | 2.49 GHz |
| Cluster 1 | 2 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 2.85 GB |
AI Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
337
62.6 IPS |
|
|
Image Classification (HP)
|
100% |
660
122.7 IPS |
|
|
Image Classification (Q)
|
96% |
542
101.2 IPS |
|
|
Image Segmentation (SP)
|
100% |
416
6.75 IPS |
|
|
Image Segmentation (HP)
|
100% |
744
12.1 IPS |
|
|
Image Segmentation (Q)
|
99% |
798
13.0 IPS |
|
|
Pose Estimation (SP)
|
100% |
1173
1.37 IPS |
|
|
Pose Estimation (HP)
|
100% |
1194
1.39 IPS |
|
|
Pose Estimation (Q)
|
96% |
1110
1.30 IPS |
|
|
Object Detection (SP)
|
100% |
369
29.3 IPS |
|
|
Object Detection (HP)
|
99% |
721
57.2 IPS |
|
|
Object Detection (Q)
|
92% |
604
48.2 IPS |
|
|
Face Detection (SP)
|
100% |
936
11.1 IPS |
|
|
Face Detection (HP)
|
100% |
1801
21.4 IPS |
|
|
Face Detection (Q)
|
100% |
1233
14.7 IPS |
|
|
Depth Estimation (SP)
|
100% |
979
7.54 IPS |
|
|
Depth Estimation (HP)
|
98% |
1674
12.9 IPS |
|
|
Depth Estimation (Q)
|
85% |
1545
12.1 IPS |
|
|
Style Transfer (SP)
|
100% |
2338
3.01 IPS |
|
|
Style Transfer (HP)
|
100% |
4202
5.40 IPS |
|
|
Style Transfer (Q)
|
96% |
3933
5.08 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
689
25.4 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
907
33.5 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
780
28.8 IPS |
|
|
Text Classification (SP)
|
100% |
288
384.8 IPS |
|
|
Text Classification (HP)
|
100% |
562
750.5 IPS |
|
|
Text Classification (Q)
|
93% |
558
748.4 IPS |
|
|
Machine Translation (SP)
|
100% |
619
10.7 IPS |
|
|
Machine Translation (HP)
|
98% |
1065
18.4 IPS |
|
|
Machine Translation (Q)
|
98% |
1085
18.8 IPS |
